Version: 0.18

Rigid Alignment

In this tutorial we show how rigid alignment of shapes can be performed in Scalismo.

Related resources

The following resources from our online course may provide some helpful context for this tutorial:


As in the previous tutorials, we start by importing some commonly used objects and initializing the system.

import scalismo.geometry._
import scalismo.common._
import scalismo.ui.api._
import scalismo.mesh.TriangleMesh
implicit val rng = scalismo.utils.Random(42)

Quick view on Transformations

Let's start by loading and showing Paola's mesh again:

val ui = ScalismoUI()
val paolaGroup = ui.createGroup("paola")
val mesh : TriangleMesh[_3D] = MeshIO.readMesh(new"datasets/Paola.ply")).get
val meshView =, mesh, "Paola")

Scalismo allows us to perform geometric transformations on meshes.

Transformations are functions that map a given point, into a new transformed point. We find the transformations in the package scalismo.registration. Let's import the classes in this package

import scalismo.registration.{Transformation, RotationTransform, TranslationTransform, RigidTransformation}

The most general way to define a transformation is by specifying the transformation function explicitly. The following example illustrates this by defining a transformation, which flips the point along the x axis.

val flipTransform = Transformation((p : Point[_3D]) => Point(-p.x, p.y, p.z))

When given a point as an argument, the defined transform will then simply return a new point:

val pt : Point[_3D] = flipTransform(Point(1.0, 1.0, 1.0))
// pt: Point[_3D] = Point3D(-1.0, 1.0, 1.0)

An important class of transformations are the rigid transformation, i.e. a rotation followed by a translation. Due to their importance, these transformations are readily defined in scalismo.

A translation can be defined by specifying the translation vector, which is added to every point:

val translation = TranslationTransform[_3D](EuclideanVector(100,0,0))

For defining a rotation, we define the 3 Euler angles , as well as the center of rotation.

val rotationCenter = Point(0.0, 0.0, 0.0)
val rotation : RotationTransform[_3D] = RotationTransform(0f,3.14f,0f, rotationCenter)

This transformation rotates every point with approximately 180 degrees around the Y axis (centered at the origin of the space).

val pt2 : Point[_3D] = rotation(Point(1,1,1))
// pt2: Point[_3D] = Point3D(-0.9984061838821647, 1.0, -1.0015912799070552)

In Scalismo, such transformations can be applied not only to single points, but most collections of points such as triangle meshes, can be transformed by invoking the method transform on the respective object.

val translatedPaola : TriangleMesh[_3D] = mesh.transform(translation)
val paolaMeshTranslatedView =, translatedPaola, "translatedPaola")

Composing transformations

Simple transformations can be composed to more complicated ones using the compose method. For example, we can define a rigid tranformation as a composition of translation and rotation:

val rigidTransform1 = translation.compose(rotation)

In Scalismo, rigid transformations are also already predefined. We could have written instead:

val rigidTransform2 : RigidTransformation[_3D] = RigidTransformation[_3D](translation, rotation)

Exercise: Apply the rotation transform to the original mesh of Paola and show the result

Note: since the rotation is around the origin, you might have to zoom out (hold right click and drag down) to see the result.

Rigid alignment

A task that we need to perform in any shape modelling pipeline, is the rigid alignment of objects; I.e. normalizing the pose of an object with respect to some reference.

To illustrate this procedure, we transform the mesh of Paola rigidly using the rigid transformation defined above.

val paolaTransformedGroup = ui.createGroup("paolaTransformed")
val paolaTransformed = mesh.transform(rigidTransform2), paolaTransformed, "paolaTransformed")

The task is now to retrieve the transformation, which best aligns the transformed mesh with the original mesh, from the meshes alone.

Rigid alignment is easiest if we already know some corresponding points in both shapes. Assume for the moment, that we have identified a few corresponding points and marked them using landmarks. We can then apply Procrustes Analysis. Usually, these landmarks would need to be clicked manually in a GUI framework. To simplify this tutorial, we exploit that the two meshes are the same and hence have the same point ids. We can thus define landmarks programmatically:

val ptIds = Seq(PointId(2213), PointId(14727), PointId(8320), PointId(48182))
val paolaLandmarks = => Landmark(s"lm-${}", mesh.pointSet.point(pId)))
val paolaTransformedLandmarks = => Landmark(s"lm-${}", paolaTransformed.pointSet.point(pId)))
val paolaLandmarkViews = =>, lm, s"${}"))
val paolaTransformedLandmarkViews = =>, lm,

Given this lists of landmarks, we can use the method rigid3DLandmarkRegistration to retrieve the best rigid transformation from the original set of landmarks:

import scalismo.registration.LandmarkRegistration
val bestTransform : RigidTransformation[_3D] = LandmarkRegistration.rigid3DLandmarkRegistration(paolaLandmarks, paolaTransformedLandmarks, center = Point(0, 0, 0))

The resulting transformation is the best possible rigid transformation (with rotation center Point(0,0,0)) from paolaLandmarks to paolaTransformedLandmarks. Best here means, that it minimizes the mean squared error over the landmark points.

Let's now apply it to the original set of landmarks, to see how well they are transformed :

val transformedLms = => lm.transform(bestTransform))
val landmarkViews =, transformedLms, "transformedLMs")

And finally, we apply the transformation to the entire mesh:

val alignedPaola = mesh.transform(bestTransform)
val alignedPaolaView =, alignedPaola, "alignedPaola")
alignedPaolaView.color = java.awt.Color.RED